Mastering Gen AI: From Ideation to Scalable Production

Businesses across various industries are faced with the challenge of effectively leveraging generative AI to drive operational efficiency and enhance customer experiences. Identifying the most impactful use cases where generative AI can deliver substantial benefits is crucial. This talk explores how organizations can harness generative AI to develop innovative solutions that can create value for their organizations.

New York Life (NYL) modernized its on-premises data platform to enhance analytics, performance, and automation for its critical insurance operations. To meet these objectives, NYL built a scalable data lake and reporting platform on AWS using AWS Lambda, AWS Glue, Amazon RDS, and Amazon Redshift. In this session, NYL shares lessons learned from moving off its legacy platform to a modern data lake and how having a modern data foundation accelerated their generative AI journey. Learn how NYL is using Amazon SageMaker and Amazon Bedrock to improve employee productivity and front-line agent experience.

At AWS, safeguarding the security and confidentiality of customers’ workloads is a top priority. AWS Artificial Intelligence (AI) infrastructure and services have built-in security and privacy features to give customers control over their data. Join this session to learn how AWS thinks about security across the three layers of our generative AI stack, from the bottom infrastructure layer to the middle layer, which provides easy access to all the models along with tools customers need to build and scale generative AI applications, and the top layer, which includes applications that leverage LLMs and other FMs to make work easier.

As generative AI gains traction, building effective and cost-efficient solutions is paramount. This session outlines seven guiding principles for building effective and cost-efficient generative AI applications. These principles can help businesses and developers harness generative AI's potential while optimizing resources. Establishing objectives, curating quality data, optimizing architectures, monitoring performance, upholding ethics, and iterating improvements are crucial. With these principles, organizations can develop impactful generative AI applications that drive responsible innovation. Join this session to hear from Mark as he provides actionable insights for your generative AI journey.

The rapid growth of generative AI brings promising innovation but raises new challenges around its safe and responsible development and use. While challenges like bias and explainability were common before generative AI, large language models bring new challenges like hallucination and toxicity. Join this session to understand how your organization can begin its responsible AI journey. Get an overview of the challenges related to generative AI, and learn about the responsible AI in action at AWS, including the tools AWS offers. Also hear Cisco share its approach to responsible innovation with generative AI.

As customers build, deploy, and scale generative AI applications, using and managing the right set of models for the outcomes they desire becomes key. Amazon Bedrock is introducing several features designed to help customers find the right models, and help customers enhance cost-efficiency while maintaining world class performance and accuracy. Attend this session to learn about Amazon Bedrock JumpStart, Intelligent Prompt Routing, Model Distillation.

Amazon Bedrock offers a managed Retrieval Augmented Generation (RAG) capability, connecting foundation models to your data. This session explores the latest Amazon Bedrock Knowledge Bases (KBs) techniques to improve response accuracy and optimize costs. Leverage Amazon Bedrock KBs' advanced chunking, parsing, and hallucination reducing capabilities for improved accuracy. Learn how to build scalable RAG solutions, delivering contextual responses while only paying for what you use.

Amazon Bedrock Agents handle tasks autonomously, streamlining operations for businesses. In this session, you'll learn how Amazon Bedrock Agents makes it easy to build agents and teams of agents on our secure, fully-managed service. We will demonstrate how you can build solutions that tackle multi-step tasks, automate existing APIs and databases, and easily integrate knowledge bases. See how agents can enable users to engage with support chat, access real-time answers, and automate actions across external platforms. Join Mark Roy to discover how coordinated AI agents, enhanced with guardrails to prevent misuse, are delivering the next generation of AI-driven customer engagement.

AWS launches Automated Reasoning (AR) checks in Amazon Bedrock Guardrails - making AWS the first major cloud provider to use automated reasoning that helps build transparent, responsible generative AI applications. Join us to learn about AR Check - a new Guardrails policy that uses sound mathematical techniques to reduce hallucinations, validate generative AI responses, and explain them in an auditable way. See how the Guardrails policy can help users generate more accurate LLM responses on highly regulated topics such as operational workflows and HR policies; learn about the different use cases for AR checks; and discover how to get started today.

Experience the future of enterprise app development with App Studio - a generative AI-powered service that uses natural language to create enterprise-grade applications, empowers technical professionals like IT project managers, data engineers, and enterprise architects to build highly secure, scalable, and performant business applications solving critical problems in minutes, without professional developer skills.

In this session, get an overview of the generative AI capabilities of Amazon Q in QuickSight. Learn how analysts can build interactive dashboards rapidly, and discover how business users can use natural language to instantly create documents and presentations explaining data and extract insights beyond what’s available in dashboards with data Q&A and executive summaries. Hear from Availity on how 1.5 million active users are leveraging Amazon QuickSight to distill insights from dashboards instantly, and learn how they are using Amazon Q internally to increase efficiency across their business.

Join us to discover how Amazon rolled out Amazon Q Developer to thousands of developers, trained them in prompt engineering, and measured its transformative impact on productivity. In this session, learn best practices for effectively adopting generative AI in your organization. Gain insights into training strategies, productivity metrics, and real-world use cases to empower your developers to harness the full potential of this game-changing technology. Don’t miss this opportunity to stay ahead of the curve and drive innovation within your team.

While existing AI assistants focus on code generation with close human guidance, Amazon Q Developer has a unique capability called agents that can use reasoning and planning capabilities to perform multi-step tasks beyond code generation with minimal human intervention. Its agent for software development can solve complex tasks that go beyond code suggestions, such as building entire application features, refactoring code, or generating documentation. Join this session to discover new agent capabilities that help developers go from planning to getting new features in front of customers even faster.

The rapid rise of generative AI is transforming how businesses approach data and analytics, blending traditional workflows and converging analytics and AI use cases. This session covers the next generation of Amazon SageMaker, the center for all your data, analytics, and AI, with a specific focus on SageMaker Unified Studio. Learn how Unified Studio brings together familiar tools from AWS analytics and AI/ML services for data processing, SQL analytics, machine learning model development, and generative AI application development into a single environment to enable collaboration and help teams build data products faster.

Amazon S3 Tables is purpose-built to store tabular data in Apache Iceberg tables. With Amazon S3 Tables, you can create tables and set up table-level permissions with just a few clicks in the Amazon S3 console. These tables are backed by storage specifically built for tabular data, resulting in higher transactions per second and better query throughput compared to unmanaged tables in storage. Join this session to learn how you can automate table management tasks such as compaction, snapshot management, and more with Amazon S3 to continuously optimize query performance and minimize cost.

Data warehouses, data lakes, or both? Explore how Amazon SageMaker Lakehouse, a unified, open, and secure data lakehouse simplifies analytics and AI. This session unveils how SageMaker Lakehouse provides unified access to data across Amazon S3 data lakes, Amazon Redshift data warehouses, and third-party sources without altering your existing architecture. Learn how it breaks down data silos and opens your data estate with Apache Iceberg compatibility, offering flexibility to use preferred query engines and tools that accelerate your time to insights. Discover robust security features, including consistent fine-grained access controls, that help democratize data without compromises.

Organizations are building petabyte-scale data lakes on AWS to democratize access for thousands of end users. As customers design their data lake architecture for the right capabilities and performance, many are turning to open table formats (OTF) to improve the performance of their data lakes and to adopt enhanced capabilities, such as time-travel queries and concurrent updates. In this session, learn about recent innovations in AWS that make it easier to build, secure, and manage data lakes. Learn best practices to store, optimize, and use data lakes with industry-leading AWS, open source, and third-party analytics and ML tools.

Discover how Amazon SageMaker Catalog, built on Amazon DataZone, transforms data and AI governance at scale. This advanced session explores three key capabilities: centralized artifact management, unified access control, and comprehensive lineage tracking. Learn to efficiently organize data and ML assets using semantic search with AI-generated metadata. We will demonstrate implementing fine-grained permissions and setting up collaborative workflows. You will also see how SageMaker Catalog enables automated data quality monitoring and sensitive data detection. Accelerate data analytics and model development, ensure compliance, and foster collaboration - ultimately driving faster time to market for your analytics and AI initiatives while maintaining robust governance.

In this session, gain the skills needed to deploy end-to-end generative AI applications using your most valuable data. While this session focuses on the Retrieval Augmented Generation (RAG) process, the concepts also apply to other methods of customizing generative AI applications. Discover best practice architectures using AWS database services like Amazon Aurora, Amazon OpenSearch Service, or Amazon MemoryDB along with data processing services like AWS Glue and streaming data services like Amazon Kinesis. Learn data lake, governance, and data quality concepts and how Amazon Bedrock Knowledge Bases, Amazon Bedrock Agents, and other features tie solution components together.

Amazon Aurora DSQL is a new relational database that combines the best of serverless experience, Amazon Aurora performance, and Amazon DynamoDB scale. Aurora DSQL's distributed architecture is designed to make it effortless for organizations of any size to manage distributed workloads with strong consistency. In this session, we guide you through the fundamentals of Aurora DSQL. Learn how Aurora DSQL can work within your architecture, understand key considerations and tradeoffs, explore what an application architecture could look like, and more.

Amazon S3 revolutionizes data discovery by automatically generating rich metadata for every object in your Amazon S3 buckets. Powered by Amazon S3 Tables, Amazon S3 Metadata provides a queryable metadata layer that allows you to curate, discover, and use your Amazon S3 data more efficiently. With Amazon S3 Metadata, you can explore and filter your objects based on attributes like object creation time and storage class to streamline data preparation for analytics, real-time inference, and more. Join this session to learn the power of metadata-driven data management with Amazon S3 Metadata.

Learn how AWS is reimagining data streaming with end-to-end managed and serverless capabilities across core infrastructure, systems operations, data integration, data processing, and data management for customers to modernize their data platforms. Learn about new and recent innovations for collecting, processing, and analyzing streaming data, including improved scalability, high resiliency, lower latency, and native integrations with many AWS and third-party services. Join this session to discover how you can use AWS streaming solutions to build scalable, resilient data streaming applications for faster insights and improved decision-making.

To overcome the performance and scale limitations of relational databases, AWS built Amazon DynamoDB to deliver consistent single-digit millisecond performance at any scale for the most demanding applications on the planet. In this session, learn about the architecture choices for Amazon DynamoDB. Gain a better understanding of when to use DynamoDB and why it is used by over one million AWS customers to power hundreds of applications that exceed half a million requests per second. Leave with a new perspective on how to design your own applications.